woodpecker_logs

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, readOnlyHint=false and non-idempotency, and the description adds genuinely new behavior: logs are base64-decoded to text, and writes are double-gated by confirm plus an environment flag with a no-op dry-run default. It does not describe what deletion destroys irreversibly or what the get response contains, but the safety-critical gating is well disclosed and consistent with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with what the tool does and immediately followed by the write gate. The trailing 'Actions: get, delete, delete_pipeline' partially restates the enum, but it is short enough to earn its place as a quick scan aid.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the definition carries the burden of describing returns, and it only notes that logs are base64-decoded to text without saying what a get returns or how deletion responds. For a destructive, five-parameter tool at 40% schema coverage, it also omits per-action parameter requirements, so it is adequate but incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 40%: action and confirm are documented in the schema, and the description reinforces the confirm semantics and lists the action values. The remaining parameters (repo_id, step_id, pipeline_number) have no descriptions anywhere, and the definition never says which identifiers each action requires, leaving a real gap for the destructive paths.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names concrete verbs and resources: reading step logs (with base64 decoding) and deleting step or pipeline logs, plus an explicit enumeration of the three actions. The resource 'logs' is distinct from the sibling tools (cron, pipelines, repos, secrets, system), though the dual read/write framing in one sentence makes the primary purpose slightly less crisp than a single-purpose tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear operational context: writes only execute when confirm is true AND WOODPECKER_ALLOW_WRITES=true, and omitting/false yields a dry-run that sends nothing. It stops short of stating when to choose delete versus delete_pipeline or what prerequisites the repo/step/pipeline identifiers impose, so the action-selection guidance is only implied by the action names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.